Urban rail station intelligent lighting method, system, terminal and storage medium

Abstract

The present invention provides an intelligent lighting method, system, terminal and storage medium for urban rail stations, the method comprising: using a camera to collect video data of each area in the urban rail station, processing the video data, and obtaining the passenger flow of each area in the urban rail station; obtaining the illumination and power of the lights in each area of ​​the urban rail station, and establishing a mixed integer linear programming model; using a genetic algorithm to solve the mixed integer linear programming model to obtain the lighting setting parameters of the lights in all areas of the urban rail station; and using the lighting setting parameters to control the lights in each area of ​​the urban rail station. The present invention establishes a mixed integer linear programming model by combining passenger flow, illumination and power of the lights, and uses a genetic algorithm to solve it, so as to quickly obtain the lighting setting parameters of the lights in all areas of the urban rail station, so as to realize intelligent control of the intelligent lighting of the urban rail station, effectively improve the control efficiency of the lights in the urban rail station, and effectively reduce the energy consumption of the lights.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment control, and in particular to an intelligent lighting method, system, terminal and storage medium for urban rail stations. Background Art

[0002] With the acceleration of my country's urbanization process, rail transit has become the main development target in the transportation field, but its high energy consumption problem is particularly prominent. Among them, the lighting system needs to operate continuously for a long time to effectively ensure the stable operation of the subway platform, becoming the second largest source of power consumption in urban rail stations in addition to environmental control power consumption. In the operation of urban rail, the lighting of platforms, station halls and advertising light boards is a key area of ​​energy waste. In actual operation, even if the station ends operation, the lighting fixtures of the platform, station hall and advertising light boards remain on, resulting in a waste of power resources. Especially when the station is about to end operation and the passenger flow is low, the lighting fixtures still maintain the number and brightness of the morning and evening peaks. The traditional urban rail transit lighting system adopts manual control, resulting in low management efficiency and high energy consumption of lighting in urban rail stations.

[0003] Therefore, the prior art has defects and needs to be improved and developed. Summary of the invention

[0004] The technical problem to be solved by the present invention is that, in view of the above-mentioned defects of the prior art, a method, system, terminal and storage medium for intelligent lighting in urban rail stations are provided, aiming to solve the problems of low management efficiency and high energy consumption of lighting in urban rail stations in the prior art.

[0005] The technical solution adopted by the present invention to solve the technical problem is as follows:

[0006] In a first aspect, an embodiment of the present invention provides an urban rail station intelligent lighting method, the method comprising:

[0007] Using cameras to collect video data of various areas in the urban rail station, processing the video data, and obtaining passenger flow in various areas in the urban rail station;

[0008] Obtaining the illumination and power of the lamps in each area of ​​the urban rail station, and establishing a mixed integer linear programming model based on the passenger flow, the illumination and the power in each area;

[0009] Solving the mixed integer linear programming model using a genetic algorithm to obtain lighting setting parameters for lights in all areas of the urban rail station;

[0010] The lighting setting parameters are used to control the lights in various areas of the urban rail station.

[0011] In one implementation, the processing of the video data to obtain passenger flow in each area of ​​the urban rail station includes:

[0012] Preprocessing the video data to obtain processed video data;

[0013] The processed video data is input into a target detection model, and after being processed by the target detection model, the passenger flow in each area of ​​the urban rail station is output.

[0014] In one implementation, preprocessing the video data to obtain processed video data includes:

[0015] Performing image scaling processing on the video data by using a bilinear interpolation method to obtain first video data;

[0016] Performing brightness adjustment and Gaussian denoising processing on the first video data in sequence to obtain second video data;

[0017] Perform image rotation correction processing on the second video data to obtain processed video data.

[0018] In one implementation, the target detection model is an improved YOLOv8 model, and the target detection model uses a C2f_DCN module to extract features of pedestrians.

[0019] In one implementation, the establishing of a mixed integer linear programming model based on the passenger flow, the illumination, and the power of each area includes:

[0020] Taking the passenger flow, illumination and power of each area as decision variables;

[0021] Establishing an objective function based on the passenger flow, the illumination and the power, wherein the objective function aims to balance the energy consumption of lamps and user comfort in the entire area of ​​the urban rail station;

[0022] The preset constraints are obtained, and the mixed integer linear programming model is obtained by combining the decision variables, the objective function and the constraints.

[0023] In one embodiment, the objective function includes a first function for minimizing energy consumption and a second function for maximizing user comfort, the first function includes the power, the second function includes the illumination and the passenger flow, and the first function and the second function are balanced by a preset weight coefficient.

[0024] In one embodiment, the mixed integer linear programming model is solved by using a genetic algorithm to obtain lighting setting parameters for lights in all areas of the urban rail station, including:

[0025] Encoding the potential values ​​of the passenger flow, the illumination, and the power into chromosome individuals to form a population, each chromosome individual representing a lighting setting parameter;

[0026] Converting the objective function of the mixed integer linear programming model into a fitness function, wherein the fitness function is used to evaluate the quality of each chromosome individual;

[0027] Using the fitness function to evaluate each chromosome individual in the population to obtain a fitness value of each chromosome individual, and using a roulette wheel selection method to select the fitness values ​​of all the chromosome individuals to obtain a plurality of first chromosome individuals;

[0028] Performing a crossover operation on the first chromosome individual to generate a second chromosome individual, and performing a mutation operation on the second chromosome individual to obtain a third chromosome individual;

[0029] Iteratively perform the selection, crossover and mutation operations of chromosome individuals until the preset end condition is reached, and obtain a final population containing several final chromosome individuals;

[0030] The final chromosome individual with the highest fitness value is selected from the final population as the lighting setting parameter for lights in all areas of the urban rail station.

[0031] In a second aspect, an embodiment of the present invention further provides an urban rail station intelligent lighting system, comprising:

[0032] A passenger flow determination module is used to collect video data of various areas in the urban rail station using a camera, process the video data, and obtain the passenger flow of each area in the urban rail station;

[0033] A model building module, used for obtaining the illumination and power of the lamps in each area of ​​the urban rail station, and building a mixed integer linear programming model based on the passenger flow, illumination and power of each area;

[0034] A parameter generation module, used to solve the mixed integer linear programming model using a genetic algorithm to obtain lighting setting parameters for lights in all areas of the urban rail station;

[0035] The parameter setting module is used to control the lights in various areas of the urban rail station using the lighting setting parameters.

[0036] In a third aspect, an embodiment of the present invention further provides a terminal, comprising: a memory, a processor, and an urban rail station intelligent lighting program stored in the memory and executable on the processor, wherein the urban rail station intelligent lighting program, when executed by the processor, implements the steps of the urban rail station intelligent lighting method as described above.

[0037] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores an urban rail station intelligent lighting program, and the urban rail station intelligent lighting program can be executed to implement the steps of the urban rail station intelligent lighting method as described above.

[0038] Beneficial effects of the present invention: The present invention collects video data of each area in the urban rail station by using a camera, processes the video data, and obtains the passenger flow of each area in the urban rail station; obtains the illumination and power of the lights in each area of ​​the urban rail station, and establishes a mixed integer linear programming model; solves the mixed integer linear programming model using a genetic algorithm to obtain the lighting setting parameters of the lights in all areas of the urban rail station; and controls the lights in each area of ​​the urban rail station using the lighting setting parameters. The present invention establishes a mixed integer linear programming model by combining the passenger flow, the illumination and power of the lights, and solves it using a genetic algorithm. It can quickly obtain the lighting setting parameters of the lights in all areas of the urban rail station, so as to realize intelligent control of the intelligent lighting of the urban rail station, effectively improve the control efficiency of the lights in the urban rail station, and effectively reduce the energy consumption of the lights. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 It is a flow chart of a preferred embodiment of the intelligent lighting method for urban rail stations in the present invention.

[0040] Figure 2 It is a schematic diagram of the architecture of the original YOLOv8 model in the present invention.

[0041] Figure 3 It is a schematic diagram of the structure of the C2f_DCN module in the present invention.

[0042] Figure 4 It is a schematic diagram of the structure of the occlusion-aware attention mechanism in the present invention.

[0043] Figure 5 It is a schematic diagram of the dynamic decoupling head module in the present invention.

[0044] Figure 6 It is a schematic diagram of various parameters in the mixed integer linear programming model of the present invention.

[0045] Figure 7 It is a functional principle block diagram of a preferred embodiment of the urban rail station intelligent lighting system of the present invention.

[0046] Figure 8 It is a terminal principle block diagram of the present invention. DETAILED DESCRIPTION

[0047] In order to make the purpose, technical solution and advantages of the present invention clearer and more specific, the present invention is further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0048] With the acceleration of my country's urbanization process, rail transit has become the main development target in the transportation field, but its high energy consumption problem is particularly prominent. Among them, the lighting system needs to operate continuously for a long time to effectively ensure the stable operation of the subway platform, becoming the second largest source of power consumption in urban rail stations in addition to environmental control power consumption. In the operation of urban rail, the lighting of platforms, station halls and advertising light boards is a key area of ​​energy waste. In actual operation, even if the station ends operation, the lighting fixtures of the platform, station hall and advertising light boards remain on, resulting in a waste of power resources. Especially when the station is about to end operation and the passenger flow is low, the lighting fixtures still maintain the number and brightness of the morning and evening peaks. The traditional urban rail transit lighting system adopts manual control, resulting in low management efficiency and high energy consumption of lighting in urban rail stations.

[0049] In view of the above-mentioned defects of the prior art, the present invention provides an intelligent lighting method, system, terminal and storage medium for urban rail stations. The method includes: using a camera to collect video data of each area in the urban rail station, processing the video data, and obtaining the passenger flow of each area in the urban rail station; obtaining the illumination and power of the lights in each area of ​​the urban rail station, and establishing a mixed integer linear programming model; using a genetic algorithm to solve the mixed integer linear programming model to obtain the lighting setting parameters of the lights in all areas of the urban rail station; and using the lighting setting parameters to control the lights in each area of ​​the urban rail station. The present invention establishes a mixed integer linear programming model by combining the passenger flow, the illumination and power of the lights, and uses a genetic algorithm to solve it. It can quickly obtain the lighting setting parameters of the lights in all areas of the urban rail station, so as to realize intelligent control of the intelligent lighting of the urban rail station, effectively improve the control efficiency of the lights in the urban rail station, and effectively reduce the energy consumption of the lights.

[0050] See also Figure 1 The urban rail station intelligent lighting method described in the embodiment of the present invention comprises the following steps:

[0051] Step S100: using a camera to collect video data of each area in the urban rail station, and processing the video data to obtain the passenger flow of each area in the urban rail station.

[0052] Specifically, by using cameras distributed in urban planning stations to collect video data from different areas, and then processing the video data, the passenger flow corresponding to each area can be obtained.

[0053] In one implementation, the processing of the video data to obtain passenger flow in each area of ​​the urban rail station includes:

[0054] Preprocessing the video data to obtain processed video data;

[0055] The processed video data is input into a target detection model, and after being processed by the target detection model, the passenger flow in each area of ​​the urban rail station is output.

[0056] Specifically, after obtaining the video data of each area, the video data is first preprocessed to obtain processed video data. Then, the processed video data is processed using a target detection model to identify people in different areas, thereby obtaining the passenger flow of each area. In the prior art, there are means of detecting passenger flow through sensors such as infrared sensors and radar sensors. However, it is prone to omissions or false alarms when the flow is large or the environment is complex. At the same time, there is also a method of using deep learning technology to predict the passenger flow in the subway station during the next target period based on historical passenger flow data, but the accuracy of the predicted data needs to be improved. The present invention uses a camera to monitor each area, and can obtain the passenger flow of each area with high accuracy and efficiency.

[0057] In one implementation, preprocessing the video data to obtain processed video data includes:

[0058] Performing image scaling processing on the video data by using a bilinear interpolation method to obtain first video data;

[0059] Performing brightness adjustment and Gaussian denoising processing on the first video data in sequence to obtain second video data;

[0060] Perform image rotation correction processing on the second video data to obtain processed video data.

[0061] Specifically, in order to match the video data obtained by the camera with the input size of the target detection model, the video data needs to be scaled from the original size to the input size required by the target detection model. In the present invention, the image scaling process uses a bilinear interpolation method, using the values ​​of four adjacent pixels for weighted averaging to provide a better scaling effect. The formula for this process is as follows:

[0062]

[0063] Among them, I new (x′, y′) represents the pixel value of the new pixel point (x′, y′) after interpolation, I(x m ,y n) represents the values ​​of four adjacent known pixels in the original image. Among them, x0 = x', x1 = x'+1, y0 = y', y1 = y'+1, (1-|x'-x m |) and (1-|y′-y n |) is the interpolation weight, which represents the distance between the target point and the adjacent pixel points in the x and y directions.

[0064] In order to make the target detection model have good recognition accuracy in low light conditions, it is necessary to adjust the brightness of the image according to the ambient light conditions of the camera to make the image details clearer. At the same time, in order to reduce the impact of noise on the model performance, a Gaussian filter is used to remove noise in the image and reduce detection interference. The Gaussian filter is a convolution kernel based on the Gaussian function. The form of the two-dimensional Gaussian function is:

[0065]

[0066] Among them, σ is the standard deviation, which determines the width of the Gaussian function, that is, the smoothness of the filter. x and y are the coordinates of the pixel in the image. In the process of Gaussian filtering, the Gaussian convolution kernel is first generated according to the given standard deviation σ. The size of the kernel is usually chosen as:

[0067] (2k+1)(2k+1),k≈3σ (3)

[0068] Among them, k is the radius of the Gaussian kernel, and k determines the size of the convolution kernel. After the Gaussian convolution kernel is determined, the Gaussian kernel is convolved with the image. The result of the convolution is the new value of each pixel, which is the weighted average of the pixel and its surrounding pixels in the original image, and the weight is determined by the Gaussian function.

[0069] In the last step of preprocessing, image rotation correction is required. Since the camera has different angles when shooting, the image needs to be input into the target detection model after angle correction, so that the model performs more consistently and robustly when facing targets in different directions. In addition, this method can also reduce the demand for multi-angle training data and reduce deployment costs. In the process of image rotation correction, the second video data (ie, the image) is first edge detected to find the main edges in the image. Then, the Hough transform is used to detect straight lines in the image and calculate the angles of these straight lines. The Hough transform is used to detect straight lines in the image. The basic idea is to convert each point in the image space into the parameter space and find the parameters of the straight line through a voting mechanism. Among them, the parametric equation of the straight line is:

[0070] ρ=xcosθ+ysinθ(4)

[0071] Among them, ρ is the vertical distance from the origin to the line, and θ is the angle of the line. The voting mechanism is to convert the edge point (x, y) to the parameter space (ρ, θ) and accumulate the counts. Finally, calculate the average of all detected straight line angles, and this average is the angle that the image needs to be rotated. Use the calculated rotation angle to rotate the image. The rotation matrix formula is:

[0072]

[0073] Among them, center x and center y is the center coordinate of the image. Using the rotation matrix to perform affine transformation on the image can obtain the image frame after rotation correction, that is, the processed video data.

[0074] In one implementation, the target detection model is an improved YOLOv8 model, and the target detection model uses a C2f_DCN module to extract features of pedestrians.

[0075] Specifically, the architecture diagram of the original YOLOv8 model is as follows Figure 2 As shown. The C2f module is used in the backbone network of the original YOLOv8 model to optimize feature extraction. The present invention improves the original YOLOv8 model by using the C2f_DCN module designed by deformable convolution to improve the backbone network. Its structural diagram is shown in Figure 3 As shown in the figure. The improvement is to use 1×1 convolution to change the number of channels for the input features, and then use Split operation instead of 1×1 convolution to split the features. By stacking multiple deformable convolution modules to increase the network receptive field, and using more jump connections, while reducing the number of parameters, a structure with richer gradient flow is obtained, which can extract richer multi-scale pedestrian features. By extracting richer multi-scale pedestrian features, the network's ability to extract features is enhanced, effectively solving the problem of extracting small-scale pedestrian features.

[0076] At the same time, the original YOLOv8 uses the attention mechanism of the convolutional block attention module (CBAM), which includes a channel attention module and a spatial attention module. In crowded environments such as urban rail stations, occlusion between passengers is a common phenomenon. The present invention adds an occlusion-aware attention mechanism to the attention mechanism of the original YOLOv8 model to enhance its ability to handle occluded scenes. The occlusion-aware attention mechanism can improve the detection accuracy of the model when some targets are occluded by paying attention to the features of the occluded area.

[0077] The schematic diagram of the occlusion-aware attention mechanism structure is as follows Figure 4As shown in the figure, global average pooling (GAP) and global maximum pooling (GMP) operations can be performed on the input feature map. Global average pooling helps to blur details and maintain the overall distribution characteristics, while global maximum pooling effectively captures key local information of small-sized and occluded pedestrians. Combining the results of these two pooling methods can fully absorb feature information of different scales, enhance the recognition and description capabilities of small-sized and occluded pedestrian features, and also reduce the risk of information loss that may be caused by using only a single aggregation method.

[0078] In the original YOLOv8 model, the main function of the detection head is to receive the feature map extracted from the backbone network and perform further processing to predict the bounding box and category of the target. Based on the original YOLOv8 model detection head, the present invention sets a dynamic decoupling head module, and its module diagram is shown in the figure. Figure 5 The dynamic decoupling head module of the present invention significantly improves the detection accuracy and robustness in dense pedestrian scenes through adaptive adjustment, multi-scale feature fusion and task decoupling design.

[0079] The present invention uses an improved YOLOv8 model for real-time passenger flow monitoring, taking the video stream obtained by the camera at the urban rail station as input to generate bounding boxes and category predictions. For passenger flow monitoring tasks, usually only the pedestrian category is concerned, so when training the model, the training set only contains pedestrian targets, and the number of these bounding boxes is counted, that is, the number of passengers in the current video frame can be obtained.

[0080] See also Figure 1 The urban rail station intelligent lighting method described in the embodiment of the present invention comprises the following steps:

[0081] Step S200: Obtain the illumination and power of the lights in each area of ​​the urban rail station, and establish a mixed integer linear programming model based on the passenger flow, the illumination and the power in each area.

[0082] Specifically, the optimization model used in the present invention is a mixed integer linear programming model (MLIP model).

[0083] In one implementation, the establishing of a mixed integer linear programming model based on the passenger flow, the illumination, and the power of each area includes:

[0084] Taking the passenger flow, illumination and power of each area as decision variables;

[0085] Establishing an objective function based on the passenger flow, the illumination and the power, wherein the objective function aims to balance the energy consumption of lamps and user comfort in the entire area of ​​the urban rail station;

[0086] The preset constraints are obtained, and a mixed integer linear programming model is obtained by combining the decision variables, the objective function and the constraints.

[0087] Specifically, the present invention sets up illumination, power consumption and passenger flow as decision variables, and the optimization goal is to balance energy consumption and comfort, and find a better lighting strategy so that the sum of total energy consumption and total discomfort (negative value indicates the emphasis on comfort) is minimized. Constraints include meeting national illumination standards, power limits, and the relationship between illumination and passenger flow. The mixed integer linear programming model of the present invention can provide accurate and efficient lighting control solutions in different time periods and regions, thereby achieving the purpose of intelligence and energy saving.

[0088] In the present invention, the meanings of the parameters in the mixed integer linear programming model are as follows: Figure 6 The model building process is as follows:

[0089] First, determine the decision variables of the model. i,t It is a key factor that directly affects passenger comfort and safety. Selecting illumination as a decision variable can ensure that the lighting in the station can meet national standards and provide a good riding experience under different time and passenger flow conditions; power consumption is directly related to energy consumption. By combining power consumption P i,t As a decision variable, it can optimize the use of electricity while meeting the lighting demand, thus achieving the goal of energy conservation and emission reduction; passenger flow reflects the density and flow of passengers in the station, and is the main factor determining the illumination demand. Adjusting the lighting according to the real-time passenger flow can avoid energy waste, adapt to the needs of instantaneous changes, and improve the flexibility and response speed of the system. i,t is also identified as a decision variable.

[0090] Secondly, the objective function is designed. Since the optimization goal is to balance energy consumption and comfort, it is necessary to minimize the energy consumption and maximize the comfort relationship function. The objective function of the present invention includes a first function for minimizing energy consumption and a second function for maximizing user comfort. The first function includes the power, and the second function includes the illumination and the passenger flow. The first function and the second function are balanced by a preset weight coefficient. The objective function expression of the mixed integer linear programming model of the present invention is as follows:

[0091]

[0092] The double summation symbol It means to sum all regions i from 1 to n and all time periods t from 1 to T, and perform cumulative calculations on all regions and all time periods; αP i,tIt represents the energy consumption of region i at time t multiplied by a weight coefficient. The purpose of this term is to weight the energy consumption, that is, the importance attached to energy consumption; -(1-α)f(C i,t ,L i,t ) represents the passenger flow C of area i at time t i,t Multiply by the illuminance L i,t and a weight coefficient (1-α) to weight comfort; α and (1-α): these two coefficients are used to balance energy consumption and comfort. The specific values ​​are determined by historical urban rail passenger flow distribution data and expert evaluation. The larger α is, the more emphasis is placed on minimizing energy consumption; conversely, the larger (1-α) is, the more emphasis is placed on passenger comfort; minimization (min) is to make the entire sum as small as possible, which means finding an optimal lighting strategy while balancing energy consumption and comfort so that the sum of total energy consumption and total discomfort (negative values ​​indicate emphasis on comfort) is minimized.

[0093] Again, add constraints. In order to ensure that passengers in the area have a good riding experience at different times and with different passenger flows, it is necessary to ensure that the lighting brightness is not lower than the national standard value, and it cannot be too higher than the national standard value, because each lamp has a rated power, and exceeding its rated value will cause damage to the lamp and create a safety hazard. While ensuring the safety of passengers, the lighting brightness can be adjusted by real-time passenger flow. The constraints of the mixed integer linear programming model of the present invention are illumination constraint, power constraint, and the relationship between passenger flow and illumination.

[0094] The expression of illumination constraint is:

[0095]

[0096] Among them, L i,t is the illumination of area (i) at time (t), L min,t is the minimum illumination requirement for area (i), L max,t is the maximum illumination requirement for zone (i).

[0097] The expression of power constraint is:

[0098]

[0099] Among them, P max,i is the maximum power limit of area (i), P 额 The rated power for each lamp.

[0100] The functional relationship between passenger flow and illumination is expressed as:

[0101]

[0102] Among them, C i,tis the passenger flow of area (i) at time (t).

[0103] For the relationship model between illumination and passenger flow, linear model, logarithmic model, exponential model, polynomial model, power law model and piecewise linear model were fitted and evaluated. The result showed that the quadratic curve had the highest fitting degree, as shown in the following formula:

[0104]

[0105] Among them, a represents the acceleration of brightness change with passenger flow, reflecting the speed of brightness change when passenger flow increases or decreases. b represents the strength of the linear relationship between brightness and passenger flow, which affects the direction and amplitude of brightness adjustment. c represents the initial brightness or basic brightness value when passenger flow is zero, which is the minimum brightness maintained by the system under no passenger flow conditions. These coefficients will be fitted with actual data to accurately describe and predict the required illumination level under different passenger flow conditions, so as to achieve dynamic adjustment and optimize energy use.

[0106] According to the uneven temporal and spatial distribution of passenger flow in urban rail stations, regression analysis was performed through historical data to determine the specific functional relationship between illumination and passenger flow, and applied it to the optimization model.

[0107] The present invention ensures that the model can not only achieve the goal of minimizing energy consumption but also meet visual comfort and safety standards by reasonably selecting constraint conditions.

[0108] See also Figure 1 The urban rail station intelligent lighting method described in the embodiment of the present invention comprises the following steps:

[0109] Step S300: solving the mixed integer linear programming model using a genetic algorithm to obtain lighting setting parameters for lights in all areas of the urban rail station.

[0110] Specifically, by defining a fitness function, initializing a population, and performing crossover and mutation operations, an approximate optimal solution can be found in a complex optimization problem, and the approximate optimal solution can be used as the lighting setting parameter for lights in all areas of an urban rail station.

[0111] In one implementation, the mixed integer linear programming model is solved by using a genetic algorithm to obtain lighting setting parameters for lights in all areas of the urban rail station, including:

[0112] Encoding the potential values ​​of the passenger flow, the illumination, and the power into chromosome individuals to form a population, each chromosome individual representing a lighting setting parameter;

[0113] Converting the objective function of the mixed integer linear programming model into a fitness function, wherein the fitness function is used to evaluate the quality of each chromosome individual;

[0114] Using the fitness function to evaluate each chromosome individual in the population to obtain a fitness value of each chromosome individual, and using a roulette wheel selection method to select the fitness values ​​of all the chromosome individuals to obtain a plurality of first chromosome individuals;

[0115] Performing a crossover operation on the first chromosome individual to generate a second chromosome individual, and performing a mutation operation on the second chromosome individual to obtain a third chromosome individual;

[0116] Iteratively perform the selection, crossover and mutation operations of chromosome individuals until the preset end condition is reached, and obtain a final population containing several final chromosome individuals;

[0117] The final chromosome individual with the highest fitness value is selected from the final population as the lighting setting parameter for lights in all areas of the urban rail station.

[0118] Specifically, the decision variables such as passenger flow, illumination and power are first encoded into chromosome individuals. Since illumination, power and passenger flow among the decision variables can be discretized into different intervals, binary encoding can be used for calculation operations. According to the national standards "Urban Rail Transit Station Design Code" (GB 50157-2013), "Architectural Lighting Design Standard" (GB50034-2013) and Shenzhen Metro hourly passenger flow statistics, the specific encoding process is as follows:

[0119] First, set the illumination coding. The average illumination of the subway platform should be no less than 150 lux, and the maximum can reach 300 lux. Set the illumination range step to 10 lux, and select 4-bit binary coding. The maximum value that 4-bit binary can represent is 2. 4 -1=15, the encoding range is 0 to 15. This can cover the range between 150 lux and 300 lux, with each step increasing by 10 lux.

[0120] Secondly, for the power coding setting, the power range is from 10W to 40W, the step length is 1W, and 5-bit binary coding is selected. The maximum value that 5-bit binary can represent is 2 5 -1=31, the encoding range is 0 to 31. This can cover the range between 10W and 40W, increasing by 1W per step.

[0121] Next, set the passenger flow per hour. The passenger flow per hour ranges from 0 to 30,000 people / hour, with a step of 500 people / hour, and selects 6-bit binary encoding. The maximum value that 6 bits of binary can represent is 2. 6 -1=63, the coding range is 0 to 63. It can cover the range from 0 people / hour to 30,000 people / hour, with each step increasing by 500 people / hour.

[0122] After the encoding of the decision variables is completed, a population is formed. After the population is initialized, the fitness function is obtained to transform the complex multi-objective optimization problem of the urban rail station intelligent lighting system into a single evaluation index. In the process of transforming the objective function, considering that when the urban rail has high passenger flow, the process of increasing illumination and power demand is not necessarily linear, a nonlinear function is introduced to weight the impact of passenger flow. The formula is as follows:

[0123]

[0124] in, This item reflects the degree of deviation of illumination and is weighted according to the size of passenger flow. Among them, μ is the comfort illumination weight coefficient, δ is the comfort passenger flow weight coefficient, L target Indicates the target illumination, which refers to the illumination level that the system hopes to achieve under specific conditions, L max Indicates the maximum illumination limit, L min Indicates the minimum illumination requirement, C max Indicates the maximum passenger flow in a certain period of time during the day, αP i,t ·t represents energy consumption. Penalty represents the penalty term. In order to ensure that the values ​​of illumination and power are within the range, the penalty term is introduced to better converge to a feasible solution that meets the constraints. The formula of Penalty is as follows:

[0125] Penalty=λ1·max(0,150-L i,t )+λ1·max(0,150-L i,t )+λ2·max(0,P i,t -40) (14)

[0126] Among them, λ1 represents the illumination penalty coefficient, and λ2 represents the power penalty coefficient.

[0127] After the objective function is converted into a fitness function, each chromosome individual in the population is evaluated using the fitness function to obtain the fitness value of each chromosome individual, and the fitness values ​​of all chromosome individuals are selected using a roulette wheel selection method to obtain several first chromosome individuals. The probability of being selected can be expressed as:

[0128]

[0129] After obtaining several first chromosome individuals, the selected illumination, power and passenger flow binary codes are cross-operated using a two-point cross-over method to generate new individuals, namely, second chromosome individuals. The second chromosome individuals can be expressed as:

[0130] Child1=Parent1[0:c]+Parent2[c:d]+Parent1[d:] (16)

[0131] Child2=Parent2[0:c]+Parent1[c:d]+Parent2[d:] (17)

[0132] Among them, Parent1 represents the first parent chromosome individual; Parent2 represents the second parent chromosome individual; c represents the starting position; d represents the ending position. Two new offspring chromosome individuals Child1 and Child2 are generated by the two-point crossover method. Specifically, Child1 is composed of the first c part of Parent1, the c to d part of Parent2, and the d to the end part of Parent1. Child2 is composed of the first c part of Parent2, the c to d part of Parent1, and the d to the end part of Parent2.

[0133] After obtaining several second chromosome individuals, different combinations of illumination, power and passenger flow can be explored through mutation operations to find the optimal lighting solution. The initial mutation rate is set to 0.05. Since too high or too low mutation rates will affect the accuracy of the model, the mutation rate must be gradually adjusted through experiments and the changes in algorithm performance must be observed.

[0134] The selection, crossover, and mutation operations are repeated until the maximum number of iterations is reached or the fitness converges. The individual with the best fitness is selected from the final population as the approximate optimal solution to the lighting system optimization problem in the urban rail station, that is, the lighting setting parameters.

[0135] By using genetic algorithms to obtain the approximate optimal solution of the mixed integer linear programming control optimization model, an intelligent lighting system can be established to dynamically adjust key parameters such as the brightness and lighting range of the lighting system according to the real-time passenger flow data of different areas and time periods in the platform, thereby providing an intelligent, efficient and sustainable lighting system solution for urban rail stations.

[0136] See also Figure 1 The urban rail station intelligent lighting method described in the embodiment of the present invention comprises the following steps:

[0137] Step S400: Use the lighting setting parameters to control the lights in various areas of the urban rail station.

[0138] Specifically, after the lighting setting parameters are obtained, the lighting settings of each area are updated in a timely manner to achieve intelligent, efficient and environmentally friendly lighting.

[0139] In summary, the present invention uses a camera to collect video data of each area in the urban rail station, processes the video data, and obtains the passenger flow of each area in the urban rail station; obtains the illumination and power of the lights in each area of ​​the urban rail station, and establishes a mixed integer linear programming model; uses a genetic algorithm to solve the mixed integer linear programming model to obtain the lighting setting parameters of the lights in all areas of the urban rail station; and uses the lighting setting parameters to control the lights in each area of ​​the urban rail station. The present invention establishes a mixed integer linear programming model by combining passenger flow, illumination and power of the lights, and uses a genetic algorithm to solve it. It can quickly obtain the lighting setting parameters of the lights in all areas of the urban rail station, so as to realize intelligent control of the intelligent lighting of the urban rail station, effectively improve the control efficiency of the lights in the urban rail station, and effectively reduce the energy consumption of the lights.

[0140] In one embodiment, if Figure 7 As shown, based on the above-mentioned urban rail station intelligent lighting method, the present invention also provides an urban rail station intelligent lighting system, including:

[0141] The passenger flow determination module 100 is used to collect video data of each area in the urban rail station using a camera, process the video data, and obtain the passenger flow of each area in the urban rail station;

[0142] A model building module 200 is used to obtain the illumination and power of the lamps in each area of ​​the urban rail station, and to build a mixed integer linear programming model based on the passenger flow, illumination and power of each area;

[0143] A parameter generation module 300 is used to solve the mixed integer linear programming model using a genetic algorithm to obtain lighting setting parameters for lights in all areas of the urban rail station;

[0144] The parameter setting module 400 is used to control the lights in various areas of the urban rail station using the lighting setting parameters.

[0145] It should be noted that the aforementioned explanation of the embodiment of the urban rail station intelligent lighting method is also applicable to the urban rail station intelligent lighting system of this embodiment, and will not be repeated here.

[0146] Based on the above embodiment, the present invention further provides a terminal, whose principle block diagram can be shown as follows: Figure 8As shown. The terminal includes a processor, a memory, a network interface and a display screen connected via a system bus. The processor of the terminal is used to provide computing and control capabilities. The memory of the terminal includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and an intelligent lighting program for urban rail stations. The internal memory provides an environment for the operation of the operating system and the intelligent lighting program for urban rail stations in the non-volatile storage medium. The network interface of the terminal is used to communicate with an external terminal via a network connection. When the intelligent lighting program for urban rail stations is executed by the processor, the steps of any of the above-mentioned intelligent lighting methods for urban rail stations are implemented. The display screen of the terminal may be a liquid crystal display screen or an electronic ink display screen.

[0147] Those skilled in the art will understand that Figure 8 The principle block diagram shown in the figure is only a block diagram of a partial structure related to the scheme of the present invention, and does not constitute a limitation on the terminal to which the scheme of the present invention is applied. The specific terminal may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0148] In one embodiment, a terminal is provided, comprising a memory, a processor, and an urban rail station intelligent lighting program stored in the memory and executable on the processor, wherein the urban rail station intelligent lighting program, when executed by the processor, implements the steps of any one of the urban rail station intelligent lighting methods provided in the embodiments of the present invention.

[0149] An embodiment of the present invention further provides a computer-readable storage medium, on which an urban rail station intelligent lighting program is stored. When the urban rail station intelligent lighting program is executed by a processor, the steps of any one of the urban rail station intelligent lighting methods provided in the embodiments of the present invention are implemented.

[0150] It should be understood that the serial numbers of the steps in the above embodiments do not imply a sequence of execution, and the execution sequence of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0151] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the above-mentioned system can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0152] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0153] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0154] In the embodiments provided by the present invention, it should be understood that the disclosed system / terminal device and method can be implemented in other ways. For example, the system / terminal device embodiments described above are only illustrative, for example, the division of the above modules or units is only a logical function division, and in actual implementation, other division methods can be used, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0155] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, it should be understood by those skilled in the art that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features therein may be replaced by equivalents. However, these modifications or replacements do not deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.

Claims

1. An intelligent lighting method for urban rail stations, characterized in that: The method comprises: Using cameras to collect video data of various areas in the urban rail station, processing the video data, and obtaining passenger flow in various areas in the urban rail station; Obtaining the illumination and power of the lamps in each area of ​​the urban rail station, and establishing a mixed integer linear programming model based on the passenger flow, the illumination and the power in each area; Solving the mixed integer linear programming model using a genetic algorithm to obtain lighting setting parameters for lights in all areas of the urban rail station; Using the lighting setting parameters to control the lights in various areas of the urban rail station; The mixed integer linear programming model is established based on the passenger flow, the illumination and the power of each area, including: Taking the passenger flow, illumination and power of each area as decision variables; Establishing an objective function based on the passenger flow, the illumination and the power, wherein the objective function aims to balance the energy consumption of lamps and user comfort in the entire area of ​​the urban rail station; Obtaining preset constraints, combining the decision variables, the objective function and the constraints, to obtain a mixed integer linear programming model; The objective function includes a first function for minimizing energy consumption and a second function for maximizing user comfort, the first function includes the power, the second function includes the illumination and the passenger flow, and the first function and the second function are balanced by a preset weight coefficient.

2. The intelligent lighting method for urban rail stations according to claim 1, characterized in that: The video data is processed to obtain the passenger flow of each area in the urban rail station, including: Preprocessing the video data to obtain processed video data; The processed video data is input into a target detection model, and after being processed by the target detection model, the passenger flow in each area of ​​the urban rail station is output.

3. The intelligent lighting method for urban rail stations according to claim 2, characterized in that: The preprocessing of the video data to obtain processed video data includes: Performing image scaling processing on the video data by using a bilinear interpolation method to obtain first video data; Performing brightness adjustment and Gaussian denoising processing on the first video data in sequence to obtain second video data; Perform image rotation correction processing on the second video data to obtain processed video data.

4. The intelligent lighting method for urban rail stations according to claim 2, characterized in that: The target detection model is an improved YOLOv8 model, and the target detection model uses the C2f_DCN module to extract the features of pedestrians.

5. The intelligent lighting method for urban rail stations according to claim 1, characterized in that: The mixed integer linear programming model is solved by using a genetic algorithm to obtain lighting setting parameters for lights in all areas of the urban rail station, including: Encoding the potential values ​​of the passenger flow, the illumination, and the power into chromosome individuals to form a population, each chromosome individual representing a lighting setting parameter; Converting the objective function of the mixed integer linear programming model into a fitness function, wherein the fitness function is used to evaluate the quality of each chromosome individual; Using the fitness function to evaluate each chromosome individual in the population to obtain a fitness value of each chromosome individual, and using a roulette wheel selection method to select the fitness values ​​of all the chromosome individuals to obtain a plurality of first chromosome individuals; Performing a crossover operation on the first chromosome individual to generate a second chromosome individual, and performing a mutation operation on the second chromosome individual to obtain a third chromosome individual; Iteratively perform the selection, crossover and mutation operations of chromosome individuals until the preset end condition is reached, and obtain a final population containing several final chromosome individuals; The final chromosome individual with the highest fitness value is selected from the final population as the lighting setting parameter for lights in all areas of the urban rail station.

6. An intelligent lighting system for urban rail stations, characterized in that: include: A passenger flow determination module is used to collect video data of various areas in the urban rail station using a camera, process the video data, and obtain the passenger flow of each area in the urban rail station; A model building module, used for obtaining the illumination and power of the lamps in each area of ​​the urban rail station, and building a mixed integer linear programming model based on the passenger flow, illumination and power of each area; The mixed integer linear programming model is established based on the passenger flow, the illumination and the power of each area, including: Taking the passenger flow, illumination and power of each area as decision variables; Establishing an objective function based on the passenger flow, the illumination and the power, wherein the objective function aims to balance the energy consumption of lamps and user comfort in the entire area of ​​the urban rail station; Obtaining preset constraints, combining the decision variables, the objective function and the constraints, to obtain a mixed integer linear programming model; The objective function includes a first function for minimizing energy consumption and a second function for maximizing user comfort, the first function includes the power, the second function includes the illumination and the passenger flow, and the first function and the second function are balanced by a preset weight coefficient; A parameter generation module, used to solve the mixed integer linear programming model using a genetic algorithm to obtain lighting setting parameters for lights in all areas of the urban rail station; The parameter setting module is used to control the lights in various areas of the urban rail station using the lighting setting parameters.

7. A terminal, characterized in that: The terminal includes a memory, a processor, and an urban rail station intelligent lighting program stored in the memory and executable on the processor. When the urban rail station intelligent lighting program is executed by the processor, the steps of the urban rail station intelligent lighting method as described in any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores an urban rail station intelligent lighting program. When the urban rail station intelligent lighting program is executed by the processor, the steps of the urban rail station intelligent lighting method according to any one of claims 1 to 5 are implemented.

Images